Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    programming language keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Seymour
    0.41
    دم
    0.40
     Nicholls
    0.40
    カップ
    0.39
     makalah
    0.39
     Mare
    0.39
    プラン
    0.39
     Nichols
    0.38
     présentant
    0.38
     kampung
    0.38
    POSITIVE LOGITS
    breviation
    0.57
    private
    0.52
     helper
    0.41
    back
    0.41
    lected
    0.40
    माना
    0.40
    checkFor
    0.39
    tcpHeader
    0.39
     होना
    0.38
    ift
    0.38
    Act Density 0.042%

    No Known Activations